AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation.

arXiv:2603.07427v3 Announce Type: replace Abstract: As Large Language Models (LLMs) evolve into autonomous agents, existing safety evaluations face a fundamental trade-off: manual benchmarks are costly, while LLM-based simulators are scalable but suffer from l